Information Theory
Asymptotic Bounds on Generalized Covering Radii of Binary Primitive BCH Codes
Maosheng Xiong, Chi Hoi Yip and Ferdinando Zullo
Fix integers $e\ge2$ and $r\ge1$. In this paper we study the $r$-th generalized covering radius $\rho_r\left(BCH(e,m)\right)$ of the binary primitive $e$-error-correcting BCH code $BCH(e,m)$. By using an algebraic-
geometric reformulation of the covering problem together with an explicit Lang-Weil estimate, we prove that \[\rho_r\bigl(\BCH(e,m)\bigr)\le(r+1)e-1\] for all sufficiently large $m$. For $e\ge7$, this improves a recent result of Belinsky–Zabokritskiy. Our proof gives a substantially simpler
geometric approach to this upper bound. In particular it implies that \[\rho_2\bigl(BCH(e,m)\bigr)=3e-1\] for all sufficiently large $m$. Previously it was only known that \[\rho_2\bigl(\BCH(e,m)\bigr) \in \left\{3e-1,3e\right\}\] for all sufficiently large $m$.
Read the full abstract ▾
Machine Learning
Branch Geometry and Finite-Radius Sensitivity of Hard-ReLU Training
Xiaoyang Li, Runni Zhou and Xinghao Yan
Outer-learning
algorithms use infinitesimal sensitivities to propose finite changes to initialization or training parameters. For hard-ReLU training, the derivative of the finite program and the derivative of its flow limit do not by themselves specify the response at a chosen radius. We characterize the intervening regime in which the perturbation radius is proportional to the GD step. Integer event rounding then survives at leading order: smooth Euler bias shifts each discrete phase, and upstream rounding moves downstream branch boundaries. We derive the crossing indices and a uniform endpoint expansion for finitely many separated transverse events in piecewise-$C^2$ dynamics, away from recursive phase boundaries. In contractive affine regions, an explicit remainder and complete branch verification certify finite candidate comparisons. Scalar phase frequencies and a coupled feedback ablation test the mechanism; frozen nonlinear-network experiments show radius-dependent prediction accuracy, including incomplete branch matches and failed-word tails. Together with local AD and uniform flow consistency, the result identifies sufficient response regimes: differentiating training is a choice of perturbation resolution as well as a choice of derivative.
Read the full abstract ▾
Computer Vision
LOCI: A Locator-Critic with Refinement Loop
Walid Bousselham, Mathilde Caron, Arsha Nagrani et al. (+1 more)
Vision-
Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level
reasoning, but instead failing to locate critical details in the image. Due to this shortcoming, VLMs generate often plausible but incorrect
reasoning based on flawed perceptual grounding. To address this, we propose Locator-Critic (LOCI), a training-free framework that decouples visual search from evidence verification. LOCI employs a Locator
agent to propose candidate visual evidence and a separate Critic
agent to evaluate its relevance and sufficiency. These
agents engage in an iterative refinement loop, progressively improving the evidence until it is adequate to answer the given question. This decoupled, self-correcting process yields substantial performance gains, achieving state-of-the-art results on multiple complex visual
benchmarks. LOCI improves accuracy for both open-weight models like Qwen3-VL (+12.1 on V*, +5.8 on HR-Bench and +11.2 on VisualProbe-Hard) and proprietary models like Gemini 2.5 Pro (+8.9 on V*, +4.3 on HR-Bench, +4.8 on VisualProbe-Hard).
Read the full abstract ▾
All authors Walid Bousselham, Mathilde Caron, Arsha Nagrani, Cordelia Schmid
Computational Engineering
Viable Pool Sizing for On-Chain FX Liquidity: Amplification, Capital, and Resilience
Ryan Fang, Ivan Bardziyan, Jessica Wang et al. (+1 more)
Financial institutions deploying on-chain FX liquidity face a joint design problem: how much capital to commit, and how to configure the pool, to remain both competitive on trading costs and profitable as a liquidity provider? The StableSwap mechanism (Egorov, 2020) interpolates between constant-product (CPMM) and constant-sum (CSMM)
market makers (Port and Tiruviluamala, 2022) via an amplification factor A, but neither extreme suits institutional FX: CPMM pools require excessive capital and generate high impermanent loss; CSMM pools are capital-efficient near the peg but drain rapidly under
adversarial flow. Using a Merton jump-
diffusion price process (Merton, 1976) and the loss-versus-rebalancing (LVR) framework (Milionis et al., 2022), we map the joint (A, TVL) space to identify configurations that satisfy all three institutional requirements: competitive slippage, positive return, and shock resilience. Minimum viable pool size scales approximately as TVL/Q = 1000/A; ROC at that minimum is thin (about 0.054% per horizon) and independent of A; low-A pools (A <= 10) suffer slippage exceeding 200 bps under a 10x shock, while high-A pools (A >= 500) suffer reserve drain up to 60%, establishing both a capital floor and a practical amplification ceiling.
Read the full abstract ▾
All authors Ryan Fang, Ivan Bardziyan, Jessica Wang, Mayank Anand
Computers and Society
Taking the Whys Seriously: Limitations of Counterfactual Explanations in Justification and Recourse
Mattia Cerrato, Otto Sahlgren and Xenia Heilmann
Counterfactual explanations (CEs) are widely used in explainable artificial intelligence (AI) to show how a model's outputs would change if the input features were manipulated. This technique is used for a range of tasks such as debugging models, explaining predictions, justifying decisions, and providing algorithmic recourse. In this paper, we explore the normative legitimacy of employing counterfactuals in real-life model deployment settings. We discuss the different stakes involved in these different purposes for which CEs are commonly employed, and find stricter requirements for justification and recourse. In particular, we find that naive application of CEs for justification and recourse can lead to ignoring contestable choices made throughout the machine learning (ML) pipeline, thus obfuscating that decisions and counterfactuals for those decisions are also artifacts of an organization's materialized design and governance choices. We demonstrate this with four empirical experiments involving interventions at stages of the ML pipeline “upstream" of the explanation itself, and show that these affect the generated counterfactuals. We find that an organization's choices on measurement models for feature and labels, business requirements, model validation, and the metric of model success have as much or more impact on the generated counterfactuals as the specifics of the generating method. Our findings underline the need to account for such choices upon providing justification and recourse, providing a stark reminder of the relational nature of these tasks. As putative justifications or recourse recommendations, CEs do not provide adequate answers to some important "why"-questions because they preclude consideration of whether the decision-maker ought to have acted differently.
Read the full abstract ▾
Artificial Intelligence
Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration
Jeffrey Jewett, William Solow and Sandhya Saisubramanian
Accurate action models are critical for effective planning. Existing action-model learning methods largely assume simple action representations or become computationally intractable when learning conditional and quantified effects. We present Online Hypothesis-Driven Conditional Action Model Learning (OHCAM), an online approach for learning action models with conditional and quantified effects from limited interactions with the environment. OHCAM maintains a belief over hypothesized action models and actively selects informative actions to reduce uncertainty by maximizing disagreement among competing hypotheses, while being robust to noisy observations. To enable scalability, OHCAM begins with a small set of simple action model hypotheses and expands to more complex conditions only when the current hypotheses become inconsistent with the data. Experiments on six
benchmark planning domains demonstrate that OHCAM is sample efficient in learning action models that solve substantially more tasks than baselines, even with observation noise. We validate OHCAM on two tasks using a Kinova Gen3
robot, demonstrating the real-world applicability of our approach.
Read the full abstract ▾
Hardware Architecture
Clock-Gating Insertion Strategies on an Open-Source MSP430 Core: A Reproducible PPA Study and a Gate-Level Simulation Caveat
Xingran Huang, Qiming Guo, Jinwen Tang et al. (+2 more)
Clock gating, the standard technique for cutting dynamic power, is introduced either as hand-written behavioral clock gates at the register-transfer level (RTL) or as integrated clock-gating (ICG)
cells inserted automatically during synthesis; the two are widely treated as interchangeable. In this paper we show, on a real open-source 16-bit microcontroller core (openMSP430) synthesized with a 32 nm standard-
cell library, that they are not equivalent in practice: behavioral latch-based RTL gating is functionally correct in ideal RTL simulation (10/10 self-checking testcases, identical to the ungated baseline) yet fails at gate level: the gated multiplier result is never captured and reads zero, while tool-inserted ICG
cells pass gate-level simulation cleanly (10/10). We root-cause the failure to a hold race introduced by the late latch+AND gated clock, and show it persists across eight simulation configurations including full Standard Delay Format (SDF) back-annotation, not a simulator-setting artifact. We then quantify the power/area/timing (PPA) impact of three gating strengths: RTL behavioral (Opt1), synthesis ICG (Opt2), and both (Opt3), against the ungated baseline, across four workloads and three process corners (ss/tt/ff). The benefit is corner-robust: ICG (Opt2) cuts dynamic power by 74-81% and total power by 25-30% at every corner. We also show that in this leakage-dominated 32 nm regime the total-power win comes from the area/leakage reduction that gating brings (leakage -24 to -30%), not from the large dynamic saving, which instead dominates active-mode energy. Our recommendation for low-power design on open-source cores is to prefer tool-inserted ICG
cells over hand-written behavioral clock gates. The full flow (Design Compiler synthesis, PrimeTime PX power, and self-checking verification) is released as an open artifact.
Read the full abstract ▾
All authors Xingran Huang, Qiming Guo, Jinwen Tang, Wenqi Jia, Dongzheng Wang
Machine Learning
One Policy Is Enough: Single-Agent Reinforcement Learning Outperforms Tree Search for Chemistry Tool Learning
Armin Dariani, Sifan Wu, Bang Liu et al. (+1 more)
Chemistry questions often demand exact computation and database lookups that a
language model cannot supply from its parameters, so it must reach for external tools. Tool use here is a three-part problem: select the right tool from a large pool, fill it with correctly typed arguments, and chain calls so that each consumes the outputs of the last. CheMatAgent, a previously published system, addresses this with hierarchical evolutionary MCTS: separate policy and execution models searching tool-call trees under two learned critics, one regressed partly onto GPT-assigned scores. We show that a single policy suffices. Our model interleaves
reasoning, tool calls, and returns in one left-to-right generation, trained by a supervised warm-up and then outcome-level reinforcement learning against a programmatic reward read directly off the gold call chain, which leaves no learned critic and no judge in the training loop. On ChemToolBench multiple-tool comprehensive chemistry, on both backbones CheMatAgent use, we improve Tool F1 by 5.5% and Return F1 by 9.6% on Qwen-2.5-7B, and by 3.7% and 3.9% on Llama-3.1-8B, compared with their strongest search configuration, at one model invocation per question, against a search whose cost grows with the tree; we also lead answer Pass Rate on Qwen-2.5-7B.
Read the full abstract ▾
All authors Armin Dariani, Sifan Wu, Bang Liu, Entao Yang
Computer Vision
Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation
Rui-Qing Sun, Chen-Hao Cui, Hui-Yang Zhao et al. (+3 more)
The rapid development of generative portrait models has raised growing concerns about
privacy leakage and identity misuse. In particular, audio-driven 3D talking face generation can reconstruct a reusable 3D portrait of a target person from a
monocular video and animate it with arbitrary
speech, making realistic identity impersonation alarmingly practical. Existing proactive defenses mainly operate in the visual domain by injecting subtle perturbations into acial regions to disrupt identity acquisition. However, such perturbations often compromise visual quality due to the strong structural priors and social sensitivity of human faces, and are easily weakened by common real-world transformations such as resizing. To overcome these limitations, we propose an imperceptible audio defense for audio-driven 3D talking face generation by shifting protection from the visual modality to the audio modality. Specifically,we exploit psychoacoustic masking to hide protective perturbations within perceptually masked frequency regions of the
speech signal, thereby reducing perceptual distortion while suppressing reliable facial animation. Extensive experiments demonstrate that the proposed method effectively degrades 3D talking face generation while preserving favorable perceptual quality. These findings highlight psychoacoustically guided audio perturbations as a practical and promising direction for
privacy-preserving portrait protection.
Read the full abstract ▾
All authors Rui-Qing Sun, Chen-Hao Cui, Hui-Yang Zhao, Tian Lan, Zhijing Wu, Xian-Ling Mao
Information Retrieval
MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval
Seokwon Song, Sohyeon Kim and Gunhee Kim
Information
retrieval (IR) increasingly targets open-ended queries that admit diverse perspectives. Existing IR
benchmarks, however, focus primarily on closed-ended queries, while even open-ended
benchmarks largely consist of queries whose supporting documents span a single subject domain and modality. We introduce Multi$^3$IR, a
benchmark that evaluates how well retrievers cover the multifaceted perspectives of open-ended queries across diverse domains and modalities. It comprises 104.9K Stack Exchange queries, each annotated with perspective descriptions that capture the query's implicit viewpoints. We further propose
SPIN, a parameter- and label-efficient method that learns noise vectors to steer
embeddings toward diverse yet meaningful semantic directions. Experiments show that existing
multimodal retrievers suffer from single-perspective bias, while
SPIN substantially improves perspective coverage on Multi$^3$IR and generalizes well to unseen open-ended IR
benchmarks. The
dataset and experimental code are available at https://github.com/seokwon99/Multi3IR.
Read the full abstract ▾
Computation and Language
Detecting AI Impostors: How Do Middle Schoolers Identify LLM Agents in a Live Collaborative Setting?
Dan Schumacher, Pragathi Durga Rajarajan, Haven Kotara et al. (+6 more)
LLMs can imitate how people write, which raises concerns about impersonation, trust, and detection in social settings. These concerns are especially important for adolescents, who use generative AI frequently but may struggle to recognize it. We introduce DoppelBot, a cooperative social deduction game designed to study how young people detect and respond to AI impersonation. Through studies with middle schoolers, we investigate whether a DoppelBot
prompts reflection on
privacy and impersonation, how repeated exposure affects AI-detection accuracy as
agents become more personalized, and which strategies students use to identify AI doppelgängers. We find that students' detection accuracy improves over time, driven by a shift from relying on linguistic cues to leveraging shared social and contextual signals. Students also demonstrated an understanding of AI limitations such as embodiment and reflected on broader issues such as data
privacy. To support future research, we release an anonymized
dataset of game transcripts and voting behavior.
Read the full abstract ▾
All authors Dan Schumacher, Pragathi Durga Rajarajan, Haven Kotara, Roman Rendon, Kosi Atupulazi, Deepti Tagare, Ismaila Temitayo Sanusi, Fred G. Martin, Anthony Rios
Machine Learning
Reproducible macroscopic dynamics in a closed-loop human-AI learning system
Minlin Wu, Xu Fang, Yicheng Zhang et al. (+2 more)
Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adaptive-tutoring histories, we define semantic order variables before model fitting and test them in user-disjoint cohorts. The state exhibits reproducible basin-like flow and operationally defined, state-heterogeneous metastable-like kinetics. A construction-matched null distinguishes normalised-
memory relaxation from a reproducible excess field. A four-term conditional mechanism recovers population drift (r = 0.946; learner-bootstrap 95% CI, 0.935-0.955). Predictive event-level self-supervised learning recovers the state and learned-plane flow; null-referenced corrections retain directional, partial-amplitude excess-field structure without full calibration. Shuffled-order training reverses learned-plane flow on ordered trajectories; support-
alignment randomisation selectively reduces inward transport. Both axes remain linearly accessible without state supervision. Without cross-model fitting, the models share leading population drift (r = 0.866; learner-bootstrap 95% CI, 0.857-0.875) and persistence ordering; residual directions remain model-specific. These results identify an externally anchored leading-order effective field linking empirical dynamics, an interpretable mechanism and neural computation.
Read the full abstract ▾
All authors Minlin Wu, Xu Fang, Yicheng Zhang, Chenyu Zhou, Zhiyi Liu
Data Structures and Algorithms
Breaking the Exponential Barrier: The First Polynomial-Time Algorithm for the Győri-Lovász Theorem
Mohammad T. Hajiaghayi, Mahdi JafariRaviz, Alireza Kaviani et al. (+1 more)
We give the first
polynomial-time
algorithm, after half a century, for the celebrated Győri-Lovász
theorem, which resolved a
conjecture of Frank (1975). The
theorem, one of the simplest existential
theorems to explain, states that every $k$-connected graph can be partitioned into $k$ disjoint connected subgraphs of arbitrary prescribed positive sizes. This is a fundamental structural result with broad applications, such as flexible allocation of connected subnetworks of prescribed sizes in sufficiently connected cloud infrastructures. While Lovász (1977) gave a highly non-constructive proof for a stronger directed version using algebraic
topology, Győri's original constructive proof (1976) requires exponential time. Despite more than 50 years of effort, no
polynomial-time
algorithm was known even for $k>4$. Determining the computational complexity of the Győri-Lovász
theorem—whether it admits even a sub-exponential-time
algorithm or is computationally hard (in particular, PLS-complete or PPAD)—has remained one of the central open problems in algorithmic graph theory. In this paper, we finally resolve this long-standing problem by a fundamentally new proof of the existential
theorem via introducing the novel concept of flow-essential assignment, which genuinely marries matching and cut structures and yields the first
polynomial-time constructive
algorithm for the Győri-Lovász
theorem. In fact, we obtain a
polynomial-time
algorithm for Lovász's stronger directed version, whose proof was non-constructive even for DAGs; for DAGs, we further obtain a near-linear-time
algorithm. We also develop
polynomial-time
algorithms for weighted generalizations where the seminal work of Chen, Kleinberg, Lovász, Rajaraman, Sundaram, and Vetta (JACM'07) on confluent flows established only existential non-constructive results.
Read the full abstract ▾
All authors Mohammad T. Hajiaghayi, Mahdi JafariRaviz, Alireza Kaviani, Soheil Mohammadkhani
Machine Learning
Nonparametric Contextual Pricing and Inventory Learning under Censored Demand
Zean Han, Jing Liang, Ruihan Lin et al. (+2 more)
In online retailing, when a product sells out, a retailer often sees only the units sold, not how many customers would have bought it had inventory been available. However, the inventory level determines how much demand is revealed, and this information can influence subsequent decisions and future profits. We study an online selling problem in which, in each round, the seller observes a
market context and then makes pricing and stocking decisions based on censored sales data from previous rounds. The challenge is to learn a context-dependent pricing and stocking policy without assuming a particular formula for demand or observing realized profit. To overcome this difficulty, we propose a Mean-Calibrated Kernel UCB (MCK-UCB)
algorithm that turns each incomplete sales record into a reliable guide for both inventory and price decisions, using data from past rounds with similar
market conditions. This design allows us to learn while serving customers, without a separate exploration phase or the need to recover all demand hidden by stockouts. We prove the minimax optimality of the proposed
algorithm, with strictly faster rates when expected profit varies more smoothly with price. Comprehensive numerical experiments have been conducted to confirm the effectiveness of the proposed
algorithm.
Read the full abstract ▾
All authors Zean Han, Jing Liang, Ruihan Lin, Zezhen Ding, Jiheng Zhang
Sound
MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI
Laura Ibáñez-Martínez, Roser Batlle-Roca, Xavier Serra et al. (+1 more)
Generative music systems are increasingly presented as tools that democratize music creation, yet their practical suitability for musicians remains underexplored. Prior work includes openness-focused evaluation frameworks, such as MusGO (Music-Generative Open AI), as well as qualitative studies of musicians' experiences with generative systems. However, these approaches do not support systematic comparison or early-stage discovery of models for creative use. Motivated by such limitations, we introduce MusGU+, a musician-centered evaluation framework organized around three dimensions: Adaptability, Usability, and Controllability. Together, these capture whether a model can be feasibly trained or fine-tuned on personal data, integrated into real-world music workflows, and controlled in musically meaningful ways. We evaluate 10 representative generative music systems and present an interactive discovery tool that enables musicians to explore and filter models according to these criteria. While MusGO remains valuable for promoting responsible research practices, MusGU+ supports informed selection and practical adoption of generative systems by musicians.
Read the full abstract ▾
All authors Laura Ibáñez-Martínez, Roser Batlle-Roca, Xavier Serra, Martín Rocamora
Computational Engineering
Finite Element Model Updating-based Load Rating of Bridges with Incomplete As-Built Information
Mehrdad S. Dizaji, Devin K. Harris, Mohamad Alipour et al. (+3 more)
Load rating is the engineering process of determining the safe load-carrying capacity of an existing bridge structure often through analysis of its load-bearing members and their cross sections. However, when structural drawings and details of the structure are missing or insufficient for such calculations, alternative solutions must be used to infer the capacity. This study proposes a rational and consistent engineering solution for capacity inference based on structural identification (St-Id). The proposed approach uses finite element model updating (FEMU) to estimate the unknown characteristics of structures for use in an analytical load rating, which requires the development of an initial model developed in ABAQUS that can be updated based on experimental test data. ABAQUS allowed for the development of an interface with MATLAB, which facilitated the integration of an automatic iterative parameter optimization
algorithm. The optimization
algorithm developed in this investigation incorporated the features of a genetic
algorithm (GA) and a gradient-based scheme to iterate on the unknown parameters. The proposed approach was evaluated on four in-service highway bridges including two concrete slab and two T-beam structures in varying deterioration condition states, which had sufficient plans available but were treated as having varying degrees of unknown details. The results illustrated that the finite element (FE) model updating approach generated load ratings that were within 0-17% of the target load ratings while alleviating the main challenges of the existing alternatives.
Read the full abstract ▾
All authors Mehrdad S. Dizaji, Devin K. Harris, Mohamad Alipour, Abdou Ndong, Osman Ozbulut, Abdollah Bagheri
Multiagent Systems
Evidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical Referral
Qi Peng, Yi Cai, Jialin Cui et al. (+7 more)
Medical referral (directing patients to the appropriate hospital department) is a complex decision-making process requiring the synthesis of
multimodal data, including patient narratives, laboratory indicators, and radiology imaging. While Large
Language Models (LLMs) have advanced medical dialogue systems, they struggle with real-world referral tasks due to two primary limitations: (1) Information Overload, where models fixate on high-frequency disease terms while overlooking subtle but critical urgency indicators; and (2) Unstructured Collaboration, where existing multi-
agent frameworks rely on loose dialogue that leads to semantic drift and confirmation bias. To address these challenges, we introduce MASGR (Multi-
Agent Structured Graph
Reasoning), a framework that treats referral not as a classification task but as a structured graph construction problem. MASGR deploys specialized
agents to extract evidence from distinct modalities and coordinates them through a clinical
reasoning graph. This graph forces
agents to establish explicit logical connections between conflicting evidence. Furthermore, we integrate a knowledge-guided arbitration mechanism that prioritizes patient safety rules over standard diagnostic classification. Extensive experiments on real-world medical records demonstrate that MASGR significantly outperforms state-of-the-art LLMs and existing multi-
agent systems, particularly in complex cases requiring the balancing of chronic disease management and emergency intervention. The AI contribution lies in the Multi-
Agent Structured Graph
Reasoning framework that transforms unstructured multi-
agent dialogue into a verifiable logical graph construction. The engineering application is demonstrated through its deployment in a complex healthcare decision-making system to optimize the precision of complex medical referrals.
Read the full abstract ▾
All authors Qi Peng, Yi Cai, Jialin Cui, Tong Zhu, Yujuan Ding, Qingbao Huang, Tao Wang, Jiayuan Xie, Changmeng Zheng, Qing Li
Numerical Analysis · Cross-listed from quant-ph
Constrained minimax approximation for quantum signal processing
Yulong Dong, James B. Larsen, Lin Lin et al. (+1 more)
Quantum signal processing (QSP) provides a simple and efficient framework for implementing
polynomial transformations using
quantum circuits. Its classical design stage leads to a constrained minimax approximation problem: find a
polynomial of prescribed parity that approximates a target function uniformly on a fitting set while remaining bounded in magnitude by one on the domain $[0,1]$, which can be viewed as a semi-infinite constraint. Discretization converts the problem into a linear program, but feasibility at a set of finitely many sampled points does not ensure feasibility on the whole domain, especially when an optimal approximant reaches the boundary of the feasible set. We investigate two approaches to address this difficulty. A Remez exchange method combined with active-set constraint enforcement is efficient on many tested instances, but its stability depends on the target and problem geometry. We then introduce nonlinear
Fourier retraction, which uses QSP completion and phase synthesis to turn a nearly feasible
polynomial into phase factors for a feasible QSP
polynomial without increasing the degree. Across representative problems, retraction largely preserves approximation accuracy and remains effective on instances where the Remez heuristic is unstable. The resulting workflow connects classical minimax approximation and semi-infinite optimization with nonlinear
Fourier analysis, and is implemented in the qsppack software package.
Read the full abstract ▾
All authors Yulong Dong, James B. Larsen, Lin Lin, Rahul Sarkar
Robotics
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Shaoan Wang, Aocheng Luo, Fei Huang et al. (+17 more)
Embodied navigation requires
agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and
robot embodiments. Modern
vision-
language models (VLMs) already encode spatial priors for visual grounding, spatial
reasoning, and pointing, but these capabilities are rarely elicited directly for
robot control. Existing
navigation systems instead rely on task- or embodiment-specific components, fragmenting perception,
reasoning, and action while offering limited generalization. Here we present LightNav-0, a compact generalist
embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with
navigation, without task-specific prediction heads. LightNav-0 represents diverse
navigation tasks through a unified
token interface: dual-channel pointing expresses task-, scene-, and embodiment-agnostic spatial intent, while a residual vector-quantized action tokenizer maps this intent to precise, embodiment-specific trajectories. Together with temporally aware visual history compression, ER mid-training, supervised fine-tuning, and reinforcement learning, this formulation supports instruction following, open-vocabulary object
navigation, and visual tracking within a single model. The
navigation training corpus spans 2K+ scenes and 4K+ hours of
embodied navigation data. LightNav-ER, the
embodied-
reasoning checkpoint used to initialize LightNav-0, attains the highest complete-set average across 8
embodied-
reasoning benchmarks, while LightNav-0 achieves state-of-the-art
monocular success rates across all 10 public
navigation simulation settings. Real-world evaluations further demonstrate zero-shot generalization across
robot embodiments, diverse scenes, and static and dynamic targets. These results establish compact VLMs as a unified and transferable backbone for generalist
embodied navigation.
Read the full abstract ▾
All authors Shaoan Wang, Aocheng Luo, Fei Huang, Jingyi Xu, Xiaoyang Wang, Yueyu Wang, Qianli Ma, Fan Yang, Ran Mei, Jia Wei, Jiangpeng Hu, Xuhao Liu, Hongming Chen, Yuanbin Shao, Yiyang Lin, Ziliang Li, Liang Pan, Xinhang Liu, Yuntao Ma, Tingxiang Fan
Social and Information Networks
Scaled Null-Adjusted Persistence: A Multiscale Bridge between Modularity and Persistence
Alessandro Avellone, Paolo Bartesaghi, Stefano Benati et al. (+1 more)
Community detection methods must balance two competing objectives: identifying small, cohesive groups while avoiding excessive fragmentation. Modularity, the most widely adopted optimization criterion, typically merges small communities in large networks due to its resolution limit. In contrast, a persistence-based criterion promotes more granular partitions. We introduce Scaled Null-Adjusted Persistence (Scaled-NAP), a parametric family of quality functions that incorporates both these criteria. The definition exploits the exact identity between a cluster's modularity contribution and its Null-Adjusted Persistence (NAP) multiplied by its relative volume. Raising this volume factor to a parameter $\alpha\in[0,1]$ yields NAP at $\alpha=0$ and modularity at $\alpha=1$, while intermediate values control the scale of the detected partition. We derive conditions under which merging two communities improves the objective function and characterize the emergence of scale dependence, including resolution-limit behaviour on Caveman graphs. We develop the Milano
algorithm, a multilevel Louvain-style heuristic for optimizing Scaled-NAP on large networks. Experiments on weighted and unweighted Lancichinetti-Fortunato-Radicchi
benchmarks show that Scaled-NAP achieves the highest or tied-highest recovery wherever the ground truth structure is detectable, with its advantage increasing under community-size heterogeneity. Tests on three real networks with up to 1.1 million nodes confirm its capability to identify fine-grained ground-truth communities. The Milano
algorithm also turned out to be the fastest method evaluated on large networks. These results show that Scaled-NAP provides an effective and scalable bridge between modularity-based and persistence-based community detection methodologies.
Read the full abstract ▾
All authors Alessandro Avellone, Paolo Bartesaghi, Stefano Benati, Rosanna Grassi
Hardware Architecture
Beacon: LLM Multi-Agent Driven Hardware Design Space Exploration for Heterogeneous Multi-Chiplet Deep Learning Accelerators
Boyu Li, Zongwei Zhu, Qianyue Cao et al. (+2 more)
Heterogeneous multi-chiplet accelerators allow chiplets to be configured independently to better match different operator characteristics and improve inference efficiency. However, heterogeneity makes simulator evaluation expensive, limiting the number of iterations affordable for hardware design space exploration (HW-DSE). Mainstream data-driven methods rely mainly on final metrics and a few predefined states, and require many search iterations to implicitly learn the relationships between input parameters and optimization objectives, making them less effective in this setting. In practice, evaluators also generate detailed reports on execution timelines, resource utilization,
memory accesses, and communication behavior. Large
language models (LLMs) can combine domain knowledge with these reports to explicitly identify bottleneck locations, degradation causes, and parameter adjustment directions, thereby improving each design decision under limited iteration budgets. Based on this observation, we propose Beacon, a report-driven LLM multi-
agent framework for heterogeneous multi-chiplet HW-DSE. Beacon employs hierarchical
agents for bottleneck localization, root-cause diagnosis, and hardware candidate generation, together with an Analysis Toolbox and RAG
memory for closed-loop search. Under the same limited iteration budget, Beacon reduces the composite latency-energy-monetary-cost objective by 25.1%–93.5% compared with random search,
Bayesian optimization, and reinforcement learning.
Read the full abstract ▾
All authors Boyu Li, Zongwei Zhu, Qianyue Cao, Xi Li, Xuehai Zhou
Computation and Language
Annotated Surrogate Retrieval for Polish Statutory Law
Orkun Yiğit Cengiz
We present a family of
retrieval methods for Polish statutory law built on document surrogates:
language-model annotations attached to statutory articles at index time. Three designs occupy different points on the cost-quality frontier. ASCR is a surrogate cascade with reranking; ASCR-H fuses a dense list into that cascade; and DTF replaces both
language-model stages with three lexical and dense retrievers, weighted reciprocal rank fusion, and a deterministic re-scoring prior, using no model call before generation. We evaluate all three against fourteen lexical, dense, fused and ablated baselines plus four controls, on 300 questions from the 2024 and 2025 Polish bar and legal counsel entrance examinations (264 with their reference article in the corpus), over 82,508 articles from 1,133 acts. On paired McNemar tests, ASCR-H places the reference provision at rank one significantly more often than every other non-oracle configuration except one of its own ablations (eighteen of twenty comparisons significant in its favour at p < 0.005), reaching 72.3% against 61.7% for BM25 and 52.3% for dense
retrieval. The advantage is concentrated at the head and does not survive depth: it is significant at cutoffs of one and five, disappears by ten, and by twenty DTF leads on point estimate (86.0% versus 84.5%) at one ninth the latency and less than half the cost. Ablation attributes 27.6 points of rank-one accuracy to the reranking stage alone. We further report that the ranking advantage does not extend to citation accuracy, where DTF matches the oracle ceiling, and three negative results on lemmatisation, pseudo-relevance feedback and query rewriting. Surrogate annotation covers 27.0% of the corpus but every reference provision in the
benchmark, an asymmetry we disclose and discuss.
Benchmark, per-question outputs and paired significance tests are publicly available.
Read the full abstract ▾
Formal Languages and Automata
Further Remarks on Separating Words
John Nicol
We revisit questions on separating words raised by Demaine, Eisenstat, Shallit, and Wilson, together with Ebrahimnejad's follow-up to their reversal problem. For length-$n$ pairs whose difference word has $d$ runs, we prove an $O(d\log n)$ bound, extending the Hamming-distance
theorem of Demaine et al. For conjugate words, we give bounds controlled by the arithmetic of the shift. We resolve Demaine et al.'s Open Problem 2 by showing that the order of two words can change nondeterministic separation by an unbounded factor. Our reversal construction addresses Ebrahimnejad's follow-up to Open Problem 1: forward and reversed deterministic separation can differ by an unbounded factor. Since nondeterministic separation is invariant under reversal, the same construction also improves the lower bound in Open Problem 3.
Read the full abstract ▾
Sound
Stride-k Subsampling: Train-Free Audio Token Reduction for Whisper
Chanhee Cho, Junhyuk Choi and Bugeun Kim
Whisper exposes
speech through a fixed 1500-
token encoder interface, now a default representation for ASR decoders and Whisper-based
speech language models (SpeechLMs), yet its redundancy remains largely unexamined. We propose stride-k subsampling, a deterministic indexing operation that retains every k-th
token after the convolutional stem or encoder
transformer. Across five Whisper scales, k=2 preserves baseline WER at both positions, with CKA attributing this stability to acoustic overlap at the stem and
attention-induced redistribution at the encoder output. Applying stride-2 at both positions cuts audio
tokens by 75% and total GFLOPs by 52-58%, with small WER costs on most ASR
benchmarks and larger costs on harder ones. The same configuration extends to three Whisper-based SpeechLMs, yielding modest accuracy drops on stronger baselines and larger drops on weaker ones, while reducing end-to-end latency by 19.6-27.4%. Requiring no training or auxiliary computation, stride-k subsampling exploits Whisper's preprocessing redundancy, indicating that its audio-
token interface carries more capacity than downstream tasks require.
Read the full abstract ▾
Computation and Language
TRIPPULSE: Multi-Agent Travel Planning with Review-Grounded Reasoning
Priyanshu Karmakar, Borru Vijay Sai, Shubhojit Mallick et al. (+3 more)
Travel itinerary generation requires balancing strict spatio-temporal constraints with human preferences. Existing LLM-based planners mainly rely on structured attributes and pre- defined traveler personas, but real travel deci- sions are often shaped by reviews that reveal experiential factors such as comfort, safety, ser- vice quality, ambiance, crowding, and hidden risks absent from structured databases. Incor- porating such review information is therefore critical to realistic, user-centric itinerary gen- eration. We propose TRIPPULSE1, a multi-
agent framework for review-grounded travel planning. Instead of relying on a monolithic planner (and face context and
reasoning bot- tlenecks), TRIPPULSE2 decomposes itinerary generation into specialized
agents (each op- erating over localized contexts) for accom- modations, transportation, meals, attractions, and events, coordinated through a global or- chestrator with scheduling mechanisms that enforce temporal and budget feasibility. We augment TRIPCRAFT with 100K+ real-world reviews and introduce Review-Grounded Per- sona
Alignment (RGPA), an LLM-as-a-Judge metric for evaluating
alignment with human- centric travel experiences. Experiments across multiple trip durations and diverse proprietary and open-source models show that TRIPPULSE maintains strong constraint satisfaction while generating more personalized and experien- tially grounded itineraries.
Read the full abstract ▾
All authors Priyanshu Karmakar, Borru Vijay Sai, Shubhojit Mallick, Abhik Jana, Shreya Ghosh, Manish Gupta
Machine Learning
Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Stream Learning Methods
Sebastian Buschjäger, Nuwan Gunasekara and Heitor Murilo Gomes
Stream learning is commonly evaluated through predictive performance and adaptation to concept drift. However, sustained operation of a stream learner also requires predictable and bounded resource usage even on long streams. This requirement becomes even more critical when learning moves from servers to near-sensor embedded systems where
memory and processing are scarce resources. In state-of-the-art stream learning, however, we perceive a strong focus on concept drift adaptation, whereas resource usage is often an evaluation byproduct. To close this gap, we
benchmark seven representative stream classifiers on 13 real and synthetic streams under model-size budgets from 128\,KiB to approximately 8\,MiB. Our
benchmark comprises a total of 6,463 experiments. We measure failure-aware accuracy, peak model size, time to budget exhaustion, and prediction-plus-update latency. The results reveal two distinct resource failure modes. Adaptive ensembles can exceed small budgets almost immediately because of their initial footprint, even when their size remains stable thereafter. Incremental trees can fit initially but grow throughout a long stream, with HoeffdingTrees (HT) and Extremely Fast Decision Trees (EFDT) increasing by median factors of 7.37 and 5.87. Explicitly compact methods remain the only viable option under the smallest budgets, but are usually overtaken as larger budgets make adaptive ensembles competitive. Hence, many state-of-the-art methods are only partially applicable in embedded systems or for long-running systems. We therefore call on the stream-learning community to make bounded resource usage a first-class design objective alongside drift adaptation, and propose concrete steps toward this goal, including an API through which stream learners can explicitly expose and respect resource budgets.
Read the full abstract ▾
Artificial Intelligence
CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models
Wail Bouhedja, Amr Mohamed and Guokan Shang
Masked
diffusion language models predict
tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel
token refinement. Yet standard masked-
diffusion decoders use a rigid inference interface: the number of masked positions allocated to the answer is fixed before generation begins. Choosing this length is difficult. A short canvas can truncate
reasoning or code, while a long canvas wastes computation and can perturb denoising. We introduce CARVE (Counterfactual-Aware Reveal with Verified Expansion), a training-free variable-length
algorithm for masked
diffusion LMs. Starting from a shorter canvas, CARVE can grow the response during decoding by inserting additional [MASK] positions. Rather than keeping every insertion, CARVE tests a candidate expanded canvas and asks a counterfactual question: would the model make similar predictions for the unresolved positions in the original canvas if the extra masked space were present? The inserted masks are kept only when they induce low Jensen-Shannon (JS) divergence on aligned unresolved positions. This makes length growth a verified stability decision rather than a pure confidence heuristic. CARVE applies without retraining to both full-canvas and blockwise
diffusion decoders. Across code generation and mathematical
reasoning benchmarks, CARVE consistently improves average performance over fixed-length baselines across all evaluated model families. Crucially, CARVE achieves these accuracy gains while reducing inference cost, reaching half the FLOPs of fixed-length decoding in some settings.
Read the full abstract ▾
Machine Learning
Selection-Aware Stress Testing for Interactive Agents
Yang Xu, Chenang Li, Jiefu Zhang et al. (+3 more)
Agent evaluations often use one
benchmark to choose a workflow and then search for task types where its advantage weakens, so both conclusions are selected from the same data. We introduce Selection-Aware Semantic Stress Testing (\SASST{}), which learns a task reweighting from pre-execution features on discovery tasks and evaluates the same paired comparison on separate confirmation tasks. The protocol checks support and stability, uses joint bounds for all planned claims, and can return no claim. We prove conditional asymptotic validity under stated cluster assumptions. A forty-cluster audit finds Gaussian undercoverage and conservative Bonferroni $t$ bounds. In one 480-episode $\tau$-bench study, a $3.75$ point discovery gain vanished on confirmation. A second-model study likewise confirmed neither a workflow benefit nor a stable stress rule.
Read the full abstract ▾
All authors Yang Xu, Chenang Li, Jiefu Zhang, Haixiang Sun, Zhou Li, Vaneet Aggarwal
Systems and Control
Parameter Estimation of Power Electronic Converters with Differentiable Physics Simulation
Pingjunjin Tan, Chunlin Lv, Jinjun Liu et al. (+1 more)
This article proposes a differentiable physics simulation (DP simulation)-based parameter estimation method for the condition monitoring of power electronic converters. In the proposed method, the time-domain simulation of converter dynamics is embedded into a differentiable computational graph, directly linking device parameters to observed voltage and current trajectories. By formulating differentiable time-stepping operators, the nonlinear dynamics of the converter across different
circuit topologies are simulated in a unified, differentiable manner. A dc-dc buck converter is used as a representative case study. Using sparse transient samples from existing sensing channels, the method enables noninvasive parameter estimation without additional sensing hardware. Comprehensive simulation studies are conducted to evaluate the impacts of time-stepping schemes, regularization constraints, and various uncertainty sources on estimation accuracy and robustness. Subsequently, 30 distinct hardware configurations are experimentally tested for validation. The results show that the proposed method can effectively track the relative variations of health-related parameters across the critical components. This DP simulation framework provides a novel perspective for physics-informed machine learning in power electronic applications.
Read the full abstract ▾
All authors Pingjunjin Tan, Chunlin Lv, Jinjun Liu, Yang Li
Sound
Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment Separation
Lishi Zuo, Youzhi Tu, Lu Yi et al. (+4 more)
Generative modeling provides a flexible way to model mixture-conditioned source distributions, but iterative
diffusion and flow matching models are costly for long music signals. This paper studies joint vocal-accompaniment separation through latent flow matching, where a pretrained variational autoencoder (VAE) maps mixtures and sources into a compact latent space and a flow matching model generates vocal and accompaniment latents jointly. The proposed framework decouples semantic separation from acoustic velocity prediction through a Separation Encoder and a Velocity Decoder. To reduce sampling cost, we further apply latent
adversarial post-training inspired by Flow2GAN for few-step generation. Experiments show that latent
adversarial refinement can improve perceptual and separation metrics under a reduced sampling budget.
Read the full abstract ▾
All authors Lishi Zuo, Youzhi Tu, Lu Yi, Zezhong Jin, Chongxin Gan, Man-Wai Mak, KongAik Lee